Search

Most machine learning algorithms are configured by a set of hyperparameters whose values must be carefully chosen and which often considerably impact performance. To avoid a time‐consuming and irreproducible manual process of trial‐and‐error to find well‐performing hyperparameter configurations, various automatic hyperparameter optimization (HPO) methods—for example, based on resampling error estimation for supervised machine learning—can be employed. After introducing HPO from a general perspective, this paper reviews important HPO methods, from simple techniques such as grid or random search to more advanced methods like evolution strategies, Bayesian optimization, Hyperband, and racing. This work gives practical recommendations regarding important choices to be made when conducting HPO, including the HPO algorithms themselves, performance evaluation, how to combine HPO with machine learning pipelines, runtime improvements, and parallelization. This article is categorized under:Algorithmic Development > StatisticsTechnologies > Machine LearningTechnologies > Prediction [ABSTRACT FROM AUTHOR]

Background: Auditory–perceptual assessment of voice is a subjective procedure. Artificial intelligence with deep learning (DL) may improve the consistency and accessibility of this task. It is unclear how a DL model performs on different acoustic features. Aims: To develop a generalizable DL framework for identifying dysphonia using a multidimensional acoustic feature. Methods & Procedures: Recordings of sustained phonations of /a/ and /i/ were retrospectively collected from a clinical database. Subjects contained 238 dysphonic and 223 vocally healthy speakers of Chinese Mandarin. All audio clips were split into multiple 1.5‐s segments and normalized to the same loudness level. Mel frequency cepstral coefficients and mel‐spectrogram were extracted from these standardized segments. Each set of features was used in a convolutional neural network (CNN) to perform a binary classification task. The best feature was obtained through a five‐fold cross‐validation on a random selection of 80% data. The resultant DL framework was tested on the remaining 20% data and a public German voice database. The performance of the DL framework was compared with those of two baseline machine‐learning models. Outcomes & Results: The mel‐spectrogram yielded the best model performance, with a mean area under the receiver operating characteristic curve of 0.972 and an accuracy of 92% in classifying audio segments. The resultant DL framework significantly outperformed both baseline models in detecting dysphonic subjects on both test sets. The best outcomes were achieved when classifications were made based on all segments of both vowels, with 95% accuracy, 92% recall, 98% precision and 98% specificity on the Chinese test set, and 92%, 95%, 90% and 89%, respectively, on the German set. Conclusions & Implications: This study demonstrates the feasibility of DL for automatic detection of dysphonia. The mel‐spectrogram is a preferred acoustic feature for the task. This framework may be used for vocal health screening and facilitate automatic perceptual evaluation of voice in the era of big data. WHAT THIS PAPER ADDS: What is already known on this subject: Auditory–perceptual assessment is the current gold standard in clinical evaluation of voice quality, but its value may be limited by the rater's reliability and accessibility. DL is a new method of artificial intelligence that can overcome these disadvantages and promote automatic voice assessment. This study explored the feasibility of a DL approach for automatic detection of dysphonia, along with a quantitative comparison of two common sets of acoustic features. What this study adds to existing knowledge: A CNN model is excellent at decoding multidimensional acoustic features, outperforming the baseline parameter‐based models in identifying dysphonic voices. The first 13 mel‐frequency cepstral coefficients (MFCCs) are sufficient for this task. The mel‐spectrogram results in greater performance, indicating the acoustic features are presented in a more favourable way than the MFCCs to the CNN model. What are the potential or actual clinical implications of this work?: DL is a feasible method for the detection of dysphonia. The current DL framework may be used for remote vocal health screening or documenting voice recovery after treatment. In future, DL models may potentially be used to perform auditory–perceptual tasks in an automatic, efficient, reliable and low‐cost manner. [ABSTRACT FROM AUTHOR]

This paper presents a new approach to finding optimal patterns for the placement of fields of sonobuoys in a complex undersea environment. We model the problem as a biobjective one, where the aim is to minimise both sensor placement time and uncertainty over target localisation. Both objectives may be important in time‐critical localisation scenarios and our approach allows an operator to choose between different optimal solutions, favouring lower placement time or lower localisation uncertainty as operational circumstances require. We develop a two‐phase algorithm, where an offline multiobjective evolutionary phase finds initial Pareto‐non‐dominated solutions to a static problem and then an online multiobjective reinforcement learning phase finds improved solutions using updated information. We find that the evolutionary algorithm improves significantly on standard grid patterns and that the reinforcement learning algorithm improves further on the evolutionary phase. The number of sonobuoys required may also be reduced. [ABSTRACT FROM AUTHOR]

Summary: This paper is concerned with covariance intersection (CI) fusion for multi‐sensor linear time‐varying systems with unknown cross‐covariance. Firstly, a CI fusion weighted by diagonal matrix (DCI) is proposed, and it is proved to be unbiased and robust and has higher accuracy than classical CI fusion. Secondly, the genetic simulated annealing (GSA) algorithm is used for multi‐parameter optimization problem caused by diagonal matrix weights. Considering the serious time‐consuming problem in optimization process of the GSA algorithm, Back Propagation (BP) network is used to obtain the optimal weights. Eventually, the DCI based on GSA algorithm and BP network is proposed. The proposed algorithm has higher accuracy and better stability than classic CI fusion algorithms. Simulation analyses verify the effectiveness and correctness of the conclusion. [ABSTRACT FROM AUTHOR]

Chronic wounds are associated with significant clinical, economic and quality‐of‐life burden. Despite the variety of wound imaging systems available in the market for wound assessment and surveillance, few are clinically validated among patients of Asian ethnicity. We aimed to clinically validate the accuracy of a smartphone wound application (Tissue Analytics [TA], Net Health Systems Inc, Florida, USA), versus conventional wound measurements (visual approximation and paper rulers), in patients of Asian ethnicity with venous leg ulcers (VLU). A prospective cohort study of patients presenting with VLU to a specialist wound nurse clinic over a 5‐week duration was conducted. Each patient received seven wound measurements: one by a trained wound nurse clinician, and three separate wound measurements using TA on each of the iOS and Android operating systems. Inter‐rater and intra‐rater reliability between clinical and TA‐based measurements were analysed using intra‐class correlation statistics, with values of <0.5, 0.5 to 0.75, 0.75 to 0.9, and >0.9 indicating poor, moderate, good and excellent reliability, respectively. 82 patients (51% males), with a mean age at 65.8 years, completed the 5‐week study duration. 25 (30%) had underlying diabetes mellitus. Chinese, Malay and Indian ethnicity comprised 68%, 12% and 11%, respectively. The VLU healed in 26 (32%) of patients within the study period. In total, 358 wound episodes with 2334 wound images were analysed. Inter‐rater reliability for length, width and area between wound nurse measurements and TA application measurements was good (range 0.799‐0.919, P < 0.001). Separate measurements of intra‐rater reliability for length, width and area within the iOS or Android systems were excellent (range 0.967‐0.985 and range 0.977‐0.984 respectively, P < 0.001). Inter‐rater reliability between TA used on the iOS and Android systems was also excellent (0.987‐0.989, P < 0.001). Tissue Analytics, a smartphone wound application, is a useful adjunct for wound assessment and surveillance in VLU patients of Asian ethnicity. [ABSTRACT FROM AUTHOR]

Background: Digital‐first assessments leverage the affordances of technology in all elements of the assessment process: from design and development to score reporting and evaluation to create test taker‐centric assessments. Objectives: The goal of this paper is to describe the engineering, machine learning, and psychometric processes and technologies of a test security framework (part of a larger ecosystem; Burstein et al., 2021) that can be used to create systems that protect the integrity of test scores. Methods: We use the Duolingo English Test to exemplify the processes and technologies that are presented. This includes methods for actively detecting and deterring malicious behaviour (e.g., a custom desktop app). It also includes methods for passively detecting and deterring malicious behaviour (e.g., a large item bank created through automatic generation methods). We describe the certification process that each test administration undergoes, which includes both automated and human review. Additionally, we describe our quality assurance dashboard which leverages psychometric data mining techniques to monitor test quality and inform decisions about item pool maintenance. Results and Conclusions: As assessment developers transition to online delivery and to a design approach that places the test taker at the centre, it becomes increasingly important to take advantage of the tools and methodological advances in different fields (e.g., engineering, machine learning, psychometrics). These tools and methods are essential to maintaining the security of assessments so that the score reliability is sustained and the interpretations and uses of test scores remain valid. Lay Description: What is known about this topic?: As more and more testing programmes transition to test taker‐centric administrations, effective measures to prevent cheating and protect content are critical to ensure the validity and integrity of scores.Two of the most common forms of cheating in online testing are (a) having someone other than the person who has registered take the test, and (b) stealing content and providing it to others to assist them in achieving a higher score. What does this paper add?: In designing a test taker‐centric digital‐first assessment, a test security framework must inform decisions from end‐to‐end (i.e., registration, onboarding, communications regarding test taker behaviours, test preparation and practice, test administration, and post‐administrative activities including scoring).Security is safeguarded through active and passive design methods; active methods include having test takers attest that they will follow the rules governing testing and informing them that they will be videoed during testing; passive methods include a computer adaptive design that limits item exposure and test overlap rates, development of a large item pool using automated item generation, and applying artificial intelligence to review test administration videos to flag unauthorized behaviours for human review. Implications: With more educational and assessment programmes transitioning to online digital models, the paper presents a comprehensive review of security issues and identifies an integrated approach for preventing cheating and other unauthorized behaviours. [ABSTRACT FROM AUTHOR]

In binocular stereo matching, there has been a problem of low matching accuracy and noise immunity in discontinuous regions and weak‐textured regions. This paper proposes a stereo matching algorithm based on an improved adaptive support window. In the cost computation stage, first, according to the preset arm length and colour threshold, a cross‐based arm is obtained, which centres on the pixel to be matched; then the adaptive regions of the vertical arm and the horizontal arm are constructed respectively, which have different shape and size. Finally, the union of the two adaptive regions is used as the final support window of Census transform. Performance evaluations on Middlebury stereo data sets demonstrate that the proposed algorithm outperforms other seven most challenging stereo matching algorithms. The mismatching rate of this algorithm is greatly reduced, and the anti‐noise performance is also improved considerably. Because the construction of the adaptive region is based on strict criteria and comprehensive consideration, the algorithm proposed in the paper can improve the matching accuracy in the weak‐textured regions and discontinuous disparity regions. [ABSTRACT FROM AUTHOR]

In this paper, a novel algorithm based on logistic regression digital backpropagation (LR‐DBP) is proposed to mitigate the effect of dispersion and nonlinearity in a long‐distance optical transmission system. The LR‐DBP can evaluate nonlinear effects by estimating the cross‐entropy error and adjusting the structure of DBP. The experiment is setup to demonstrate an 80 Gbit/s 16QAM signal transmitted across 1000 km single‐mode fiber. The results show that LR‐DBP achieves a 1.8 dB launch power improvement over the dispersion compensation algorithm and a 0.6 dB launch power gain with DBP. The proposed algorithm could obtain with 19.2% computational complexity decrease and 19.6% central processing unit (CPU) running time decrease by calculating the average numbers of real multiplications and CPU running times. [ABSTRACT FROM AUTHOR]

Early and effective detection of wind turbine blade (WTB) surface defects can avoid complex and expensive repair problems and serious safety hazards. The traditional target detection methods have the problems of insufficient detection capability, long model inference time and low recognition accuracy for small targets and long strip defects in WTB datasets. This paper proposes a high‐precision model SOD‐YOLO for WTB surface defect detection based on UAVs image analysis of YOLOv5. First, the WTB images are preprocessed by foreground segmentation and Hough transform to build the WTB defect dataset. Then, a micro‐scale detection layer is added to the original YOLOv5, and the K‐means algorithm is used to re‐cluster anchors and add the CBAM attention mechanism to each feature fusion layer to reduce the loss of feature information for small target defects and other defects. In addition, to improve the detection efficiency, the channel pruning algorithm is used to reduce the model size. The experimental results show that the average accuracy (mAP) of the SOD‐YOLO algorithm on the WTB dataset reaches 95.1%, which is 7.82% better than YOLOv5, and the FPS is 28.3% better. Therefore, SOD‐YOLO is able to detect small target defects and other defects quickly and effectively. [ABSTRACT FROM AUTHOR]

In recent years, the rapid development of the Internet of Things (IoT) technology has provided a strong technical support for the technological transformation of the logistics industry. The informatization development of logistics industry increasingly relies on the Internet of Things technology represented by Radio Frequency Identification (RFID) technology. These technologies lead the whole business process to optimize the business process in the direction of accurate, efficient and real‐time. In order to solve the problem that the reader cannot identify the label information correctly due to the phenomenon of data collision in the application of RFID technology, this paper proposes an anti‐collision algorithm based on Slotted Random Regressive‐style Binary Search Tree (SR‐RBST). Based on Slotted ALOHA (SA) the method proposed in this paper uses the Regressive‐style Binary Search Tree (RBST) to process the RFID labels in the collision time slot. With the same size of tags, the SR‐RBST algorithm needs less total time slot and has higher efficiency and shorter identification time, while with the increase of the number of tags, the SR‐RBST anti‐collision algorithm has more obvious advantages. The SR‐RBST algorithm effectively improves the time slot utilization efficiency of the system. [ABSTRACT FROM AUTHOR]

Summary: The visibility of the image is degraded by haze components which are affected in image during image acquisition process. The haze removal process can be categorized into haze reduction from single image and haze reduction from multiple images. The second case consumes more time and the complexity of algorithm is high. In order to overcome such limitations, this paper proposes an efficient methodology for haze reduction in single acquired image. In this paper, haze detection and removing methodology is proposed using Gaussian pyramidal decomposition. This proposed methodology is tested on both indoor and outdoor haze affected images. The performance of this proposed haze removal algorithm is analyzed with respect to average running time and peak signal to noise ratio, mean square error, mean absolute error, Entropy, and normalized histogram intersection coefficient. [ABSTRACT FROM AUTHOR]

Given the widespread contribution of independent contractors to organizational innovation and competitive advantage, it is timely to reassess assumptions about the HRM practices appropriate to their management and the rationale for organizations to work with them. In the original and highly influential HR architecture model of Lepak and Snell (1999), contractor status is viewed as an outcome of the low value and/or low uniqueness of human capital resulting in the proposition to externalize and manage them using either none or minimal compliance‐based HRM practices. Developments in digital technologies and algorithmic management epitomized by online labor platforms prompt us to reconsider these assumptions and to challenge the proposed links between value/uniqueness of human capital, employment mode and HRM practices that are assumed by the HR architecture model. Using insights from online labor platforms, we argue that the significant benefits to firms of working with contractors, coupled with the possibilities offered by algorithmic management to efficiently monitor and regulate their behavior, provide a compelling reason for organizations to choose external employment modes even when workers are key to value creation. We challenge the alignment and stability of the relationships proposed by the HR architecture model, and offer propositions to extend the model by reconsidering the rationale for, and nature of, HRM practices associated with contractors. This reassessment is both timely and relevant given the growing prominence of business models where externalizing workers is central alongside the development of new forms of algorithmic human resource management to control them. [ABSTRACT FROM AUTHOR]

In 1890, Hess found new special case of integrability of Euler–Poisson equations of motion of a heavy rigid body with a fixed point. In 1892, Nekrasov proved that the solution of the problem of motion of a heavy rigid body with a fixed point under Hess conditions reduces to integrating the second‐order linear differential equation. In this paper, the corresponding linear differential equation is derived and its coefficients are presented in the rational form. Using the Kovacic algorithm, we proved that the Liouvillian solutions of the corresponding second‐order linear differential equation exist only in the case, when the moving rigid body is the Lagrange top, or in the case, when the constant of the area integral is zero. In 1890, Hess found new special case of integrability of Euler–Poisson equations of motion of a heavy rigid body with a fixed point. In 1892, Nekrasov proved that the solution of the problem of motion of a heavy rigid body with a fixed point under Hess conditions reduces to integrating the second‐order linear differential equation. In this paper, the corresponding linear differential equation is derived and its coefficients are presented in the rational form.... [ABSTRACT FROM AUTHOR]

Railway track defects must be detected and repaired to ensure the safe operation of the railway. Signals generated by wheelset contact with rail discontinuities contain information about railway track structure and health. Each signal has a characteristic pattern, which is modified in the presence of defects. Signal decomposition is commonly used to extract characteristics from impact response signals. It is necessary to select an appropriate decomposition method for the wheel/rail impact signal. This paper presents a study of the effectiveness of decomposition methods to identify the most appropriate technique for classification of rail conditions. Vibration signals have been generated in experiments and decomposed. The signal characteristics are presented and energy‐based methods are used in an evaluation of the different approaches. Standard deviation is used to assess the similarity of parameter value from different intrinsic mode functions (IMFs); maximum and minimum differences from the mean value are used to consider the effectiveness of each technique in identifying specific damage types. The evaluation shows that variational mode decomposition (VMD) is suitable for the rail application. Classifiers are applied to the outputs of the selected decomposition method. The results demonstrate the suitability of the approach for processing wheel/rail impact response signals to detect faults and improve safety. [ABSTRACT FROM AUTHOR]

This paper reports a guidance and control method for vision‐assisted deep stall landing for a fixed‐wing unmanned aerial vehicle (UAV). With a deep stall maneuver, a fixed‐wing UAV can land on a confined area with a deep flight path angle. This paper combines vision‐assisted guidance for approach and deep stall maneuvers for intuitive fixed‐wing UAV operation. A target landing area is chosen and tracked by a human operator with a computer mouse on the aerial image. Then, a line‐of‐sight vector is created to generate a guidance command. The proposed method is composed of two phases: a vision‐assisted approach (Phase I) and vision‐assisted deep stall landing (Phase II). In Phase I, the UAV is guided toward a mouse‐tracked landing area while maintaining the flight speed and altitude. In Phase II, the deep stall is initiated by a deep stall start algorithm, and the UAV is guided to the mouse‐tracked target landing area. The feasibility of the suggested method is verified by a series of flight tests, where the testbed UAV successfully landed on a 10 m × 10 m target. [ABSTRACT FROM AUTHOR]

Summary: In this paper, a new technique is suggested for best electric load forecasting of South Korea. The proposed study is based on an improved metaheuristic methodology. This paper proposes a new improved version of Support Vector Machine for Regression (SVR) base on the proposed algorithm. The algorithm is based on a modified version of Crow Search Algorithm (ACSA), where, by combining by the SVR, generates an efficient classifier. Although, different drawbacks of using original CSA are stated, the proposed ACSA method provides a proper modification for resolving of these shortcomings. The forecasting model has been then performed to a historical data from South Korea to indicate the algorithm efficiency and the results are compared with some other methods, including SVR‐CGA, SVR‐CAS, ANN, and simple Regression to show the suggested method performance. Final results show that MAPD, MSE, and RMSE values of the test data with lower values for South, North, Center, and East, provided better results based on the proposed SVR‐ACSA based on different values of center and kernel of the SVR. Experimental results on the case study shows that the minimum MAPD has been added which is happened in Northern regional is 1.1062, 1.1336, 1.1065, 1.02, 2.23, 1.96, and 1.49 for SVR‐ACSA, SVR‐CGA, SVR‐CAS, ANN, Regression, LSTM‐RNN, and ELM which indicates the method's higher efficiency. [ABSTRACT FROM AUTHOR]

The GSCP (Gauss–Seidel based projection‐contraction) algorithm has been well established in solving elastoplastic mixed complementarity problems (MiCPs) or other problems which have similar mathematical form. However, the stability problems in the GSPC algorithm may cause nonconvergence or program crashes. Thus, the method of constructing and analyzing counterexamples is adopted to study the reasons for the instability of the GSPC algorithm. The R‐GSPC algorithm was developed by modifying the part of the GSPC algorithm that caused the crash to make the algorithm stable. In addition, this paper analyzes the convergence, compatibility, and initial value impact of R‐GSPC, and finds that the R‐GSPC algorithm greatly improves the robustness and stability without losing accuracy. This paper allows the GSPC algorithm to be better extended to more fields and to be suitabled for being introduced into commercial programs. [ABSTRACT FROM AUTHOR]

This paper presents the design and implementation of the control algorithms design module based on a remote laboratory named NCSLab, which allows students, teachers, and researchers to do practical experiments with various control systems remotely via the Internet whenever and wherever they want. To meet the demand of students with different levels and provide more extensibility, a flexible control algorithm designing system is deployed using a frontend and backend separation framework. JointJS is selected to construct the graphic user interface and an algorithm server is developed to deal with the algorithms tasks. In this way, the users are able to customize control systems online with a visualized interactive interface. A control algorithm could be formed easily without programming, so the users could concentrate on the control algorithm itself. For advanced users, customized C‐MEX S‐Functions are available for extra sophisticated control systems. The designed control algorithms are converted into executable codes at the back‐end by the servers. They could be implemented into the remote test rigs and then the corresponding results would be sent back in real‐time. The overall implementation is based on the web, so only common browsers and Internet access are needed. By logging into the laboratory through the web, the users could start practical experiments quickly after acquiring the control right of the desired test rig. And the whole process, including designing, simulating, and generating codes, is integrated into the interface of the proposed system module, which is easy to use and could bring great convenience to the users. [ABSTRACT FROM AUTHOR]

Background: Deficits in the ability to use language in social contexts, including storytelling skills, are observed across the autism spectrum. Development in machine‐learning approaches may contribute to clinical psychology and psychiatry, given its potential to support decisions concerning the diagnosis and treatment of psychiatric conditions and disorders. Aims: To evaluate the usefulness of deep neural networks for detecting autism spectrum disorder (ASD) from textual utterances, specifically from narrations produced by individuals with ASD. Methods & Procedures: We examined two text encoders: Embeddings from Language Models (ELMo) and Universal Sentence Encoder (USE), and three classification algorithms: XGBoost, support vector machines, and dense neural network layer. We aimed to classify 25 participants with ASD and 25 participants with typical development (TD) based on their narrations produced during the Autism Diagnostic Observation Schedule, Second Edition (ADOS‐2) picture book task. The results of computational approaches were compared with the results of standardized testing and classifications made by two psychiatrists (raters). The raters were asked to read utterances produced by a participant (without an examiner's statements and additional information) and assign a participant to one of the two groups: ASD or with typical development (TD). Outcomes & Results: The computer‐based models had higher sensitivity, specificity, positive predictive values and negative predictive values than the raters, and lower than the two standardized instruments: ADOS‐2 and Social Communication Questionnaire (SCQ). Conclusions & Implications: Our findings lay the groundwork for future studies involving deep neural network‐based text representation models as tools for augmenting the ASD diagnosis or screening. Both ELMo and USE text encoders provided promising specificities, sensitivities, positive predictive values and negative predictive values. Our results indicate the usefulness of page‐level embeddings for utterance representation in ADOS‐2 picture book task. WHAT THIS PAPER ADDS: What is already known on this subject: Deficits in the use of language in social contexts, and narrative ability in particular, are observed across the autism spectrum. Most research on narrative skills has applied hand‐coding methods. Hitherto, machine‐learning methods were used mostly for image recognition problems and data from screening questionnaires for ASD classification. Detection of mental and developmental disorders from textual input is an emerging field for machine and deep‐learning methods. What this paper adds to existing knowledge: This study explored the ability of several types of deep neural network‐based text representation models to detect ASD. Both ELMo and USE provided the most promising values of specificity, sensitivity, positive predictive values and negative predictive values. What are the potential or actual clinical implications of this work?: Competitive accuracy, repeatability, speed and ease of operation are all advantages of computerized methods. They allow for objective and quantitative assessment of narrative ability and complex language skills. Deep neural network‐based text representation models could in the future support clinicians and augment the decision‐making process related to ASD diagnosis, screening and intervention planning. [ABSTRACT FROM AUTHOR]

Falling is a significant cause of injuries and even death in the elderly. The timely detection of the fall action helps to rescue people who may have physical health problems due to the fall, so fall detection is necessary. The traditional fall detection methods are mostly based on wearable devices, which need to be worn all the time, and the cost of the device is high. In recent years, the fall detection method based on computer vision has become a research hot spot. This paper proposes a framework for falling motion detection based on deep learning. To quickly and accurately classify human movements, a method using bone key points as the feature descriptors of human movements is proposed. The OpenPose algorithm is used to extract the human skeleton point information as the primary human body feature, and then use the deep learning method to classify further and recognise our action features. In this paper, four types of daily actions, such as falling and walking, are classified and recognised. The results show that the algorithm achieves an accuracy of 99.4% on our dataset. Simultaneously, 86.1% accuracy is reached in the public dataset fall detection dataset. [ABSTRACT FROM AUTHOR]

Summary: A sensor network is a situation‐based critical network defined under certain restrictions and constraints. The clustered architecture is defined over these networks to utilize the criticality vectors and to improve network communication. In this paper, a degree load‐balanced and fuzzy‐ACO (DLB‐fACO) protocol is proposed for optimizing the clustered architecture. In this architecture, the load analysis is performed while forming the clusters. The cluster head selection is performed based on energy, cluster density, and probability vector. The node degree‐ and energy‐balanced analysis is performed for identifying the cluster members. Once the clusters are formed, the ACO approach is applied to perform the cluster‐based hierarchical routing. Communication is performed at two levels. In the first level, node‐to‐cluster head communication is performed by considering energy and degree consideration. In the second level, the fuzzy‐integrated ACO method is applied for inter‐cluster route formation. The route optimization is here performed under fuzzy‐based energy, degree, and distance parameters. These fuzzy parameters are evaluated within the ACO algorithm for generating the optimized route. The proposed load‐balanced protocol is analyzed against the LEACH, LEACH‐C, LEACH‐CC, M‐LEACH, Fuzzy‐PSO, Fuzzy‐ACO, Fuzzy‐Cuckoo, and FMCB‐ER protocols. The experimentation results confirm the significant gain in network lifetime and packet communication. The cluster count, clustering switching, and communication failure are also reduced in comparison with existing conventional and optimized protocols. [ABSTRACT FROM AUTHOR]

This paper mainly introduces the development of 4K HDR "Stacked‐Panel" TV based on Dual‐Cell LCD. Dual‐Cell technology enables significant improvement in display contrast, but the drop of transmittance limits the increase of peak luminance. In this work, we innovatively designed the pixel control algorithm for Dual‐Cell LCD. Moreover, the peak luminance and color gamut were further improved using direct‐lit backlight and QD technology, leading to the outstanding HDR display effect. [ABSTRACT FROM AUTHOR]

Bloody Mahjong is a kind of mahjong. It is very popular in China in recent years. It not only has the characteristics of mahjong's conventional state space, huge hidden information, complicated rules, and large randomness of hand cards but also has special rules such as Change three, Hu must lack at least one suit, and Continue playing after Hu. These rules increase the difficulty of research. These special rules are used as the input of the deep learning DenseNet model. DenseNet is used to extract the Mahjong situation features. The learned features are used as the input of the classification algorithm XGBoost, and then the XGBoost algorithm is used to derive the card strategy. Experiments show that the fusion model of deep learning and XGBoost proposed in this paper has higher accuracy than the single model using only one of them in the case of high‐dimensional sparse features. In the case of fewer training rounds, accuracy of the model can still reach 83%. In the games against real people, it plays like human. [ABSTRACT FROM AUTHOR]

The ideal gas molecular movement (IGMM) as a metaheuristic optimization method is a prominent option for solving optimization problems. However, in some complex cases, IGMM may possess premature convergence or get trapped in local optima. Therefore, to tackle these issues, this paper indicates a new modified IGMM algorithm named opposition‐based IGMM, which has been incorporated with opposition based learning (OBL), Cauchy mutation (CM), velocity clamping (VC), and mirror operator (MO) to enhance its performance. OBL, VC, and MO improve the convergence of IGMM, whereas CM assists IGMM to escape local optima. The effect of each strategy, OBL, CM, VC, and MO, on IGMM, is confirmed through 30 low and high‐dimensional benchmarks, including 23 well‐known mathematical problems and CEC2017 as complex test functions and three engineering problems. Analysis results represent that integration IGMM with OBL, CM, VC, and MO has the best performance among other IGMM variants and eventually improved IGMM in exploration, exploitation, accelerating convergence, and local optima avoidance. [ABSTRACT FROM AUTHOR]

Summary: The fused lasso signal approximator (FLSA) is a smoothing procedure for noisy observations that uses fused lasso penalty on unobserved mean levels to find sparse signal blocks. Several path algorithms have been developed to obtain the whole solution path of the FLSA. However, it is known that the FLSA has model selection inconsistency when the underlying signals have a stair‐case block, where three consecutive signal blocks are either strictly increasing or decreasing. Modified path algorithms for the FLSA have been proposed to guarantee model selection consistency regardless of the stair‐case block. In this paper, we provide a comprehensive review of the path algorithms for the FLSA and prove the properties of the recently modified path algorithms' hitting times. Specifically, we reinterpret the modified path algorithm as the path algorithm for local FLSA problems and reveal the condition that the hitting time for the fusion of the modified path algorithm is not monotone in a tuning parameter. To recover the monotonicity of the solution path, we propose a pathwise adaptive FLSA having monotonicity with similar performance as the modified solution path algorithm. Finally, we apply the proposed method to the number of daily‐confirmed cases of COVID‐19 in Korea to identify the change points of its spread. [ABSTRACT FROM AUTHOR]

Background: It is vital to understand students' Self‐Regulatory Learning (SRL) processes, especially in Blended Learning (BL), when students need to be more autonomous in their learning process. In studying SRL, most researchers have followed a variable‐oriented approach. Moreover, little has been known about the unfolding process of students' SRL profiles. Objectives: We present the insights derived from a study that measured motivation and the learning strategies used by 198 students of a university entry‐level, business school, BL course to develop an understanding of students' SRL processes. Methods: The Strategies for Learning Questionnaire (MSLQ) was used to survey 198 students three times during a semester to investigate SRL profiles and how they unfolded as the course progressed using a person‐oriented approach. Through a clustering approach, we focus on MSLQ's motivation aspects as its importance has been emphasised by different SRL theories, and extant research into motivation in learning analytics (LA) is still lacking. Results and Conclusions: Through the longitudinal clustering approach, we identified minimally, average, and highly SRL profiles. We acknowledged that students might change their SRL profiles as the course progressed as a result of feedback they received. What are the 1 or 2 Major Takeaways from the Study?: This study contributes to the SRL theory by examining students' SRL profiles adaptation longitudinally (addressing the challenge identified regarding the cyclical nature of SRL). This study contributes to LA by investigating motivational constructs currently lacking in the field and bringing forward theory based empirical evidence to inform theory and practice. Lay Description: What is currently known about the subject matter: Self‐regulated learning (SRL) is important for academic achievement, especially during online learning; more research is needed to understand students' SRL and its cyclical nature.Learning analytics (LA) is an advocate for gathering and analysing data for supporting students' learning. It lacks empirical evidence based on theoretical and students' motivational studies.Institutions will benefit from more research on evidence‐based practice in Blended Learning (BL). What this paper adds to that: Evidence for the understanding of students' SRL, identifying student subgroups (different SRL profiles), and observing the cyclical nature of SRL during BL courses.We enhanced LA through the use of empirical research into motivation and its mapping of students' SRL profiles.Contribute to knowledge within BL about the dynamics of students' motivation, strategy use, and SRL, and showing that successful students better self‐regulate their learning.Evidence to support the emerging role of LA in identifying at‐risk students during BL.Evidence shows the most important motivational and learning strategy constructs that are significantly correlated with the final score in BL. The implications of study findings for practitioners: Through LA, students, educators, and institutions can benefit when universities implement BL.Enabling educators to better understand their students' SRL and how students can adapt quite different SRL profiles over time. Through this information, they can help students adopt a better profile. They also can help students in their SRL process, for example, by applying appropriate interventions.Pedagogically helps lecturers when developing the instructional and interventional design. [ABSTRACT FROM AUTHOR]

In this paper, we take advantage of the reconstruction properties of the sampling Kantorovich (SK) algorithm to estimate the volume of the human brain for the quantification of Alzheimer's biomarkers. At first, the goodness of the reconstructions is evaluated, comparing it to different interpolation methods by means of the Peak Signal to Noise Ratio (PSNR) index; then the stereological Cavalieri/Point‐counting technique is used to infer volumetric data starting from the knowledge of the planar sections. The comparison of the achieved results with synthetic references confirms the good performances of the new methodology. [ABSTRACT FROM AUTHOR]

The state‐space realization of linear systems is of utmost importance in linear systems theory. After the realization problem for the time‐invariant case was solved, particular attention was paid to the case of linear periodic systems. Recently, such systems have regained importance, for instance, in the context of coding theory where periodic convolutional encoders play an important role. The majority of the contributions within this area only concern the realization of transfer functions (or impulse responses), thus excluding the case of input/output linear systems without coprime representations. By the end of the eighties of the last century, Jan C. Willems suggested an approach (nowadays known as the behavioral approach) that considers a wider class of systems and allows to overcome this drawback. According to this approach, the central object in a system is its behavior which consists of all the signals that satisfy the system laws (also called system trajectories). Consequently, the behavior of a system with an input/output representation that is not coprime contains more trajectories than the set of input/output signals defined by the system transfer function. Our work takes this fact into account. In previous research conducted by the authors, some results on the realization of periodic behavioral systems were obtained, which, despite their importance, are conservative with respect to the dimension of the obtained realizations. In this paper, we revisit the behavioral periodic realization problem and give further insight into this question. This allows to derive new results and set up an algorithm to compute low‐dimensional state‐space realizations. [ABSTRACT FROM AUTHOR]

In this paper, we study anabelian geometry of curves over algebraically closed fields of positive characteristic. Let X•=(X,DX)$X^{\bullet }=(X, D_{X})$ be a pointed stable curve over an algebraically closed field of characteristic p>0$p>0$ and ΠX•$\Pi _{X^{\bullet }}$ the admissible fundamental group of X•$X^{\bullet }$. We prove that there exists a group‐theoretical algorithm, whose input datum is the admissible fundamental group ΠX•$\Pi _{X^{\bullet }}$, and whose output data are the topological and the combinatorial structures associated with X•$X^{\bullet }$. This result can be regarded as a mono‐anabelian version of the combinatorial Grothendieck conjecture in the positive characteristic. Moreover, by applying this result, we construct clutching maps for moduli spaces of admissible fundamental groups. [ABSTRACT FROM AUTHOR]

Anomaly detection of sequences is a hot topic in data mining. Anomaly detection using piecewise aggregate approximation in the amplitude domain (called ADPAAD) is one of the widely used methods in anomaly detection of sequences. The core step in the classical algorithm for performing ADPAAD is to construct an approximate representation of the subsequence, where the elements of each subsequence are divided into several subsections according to the amplitude domain, and then the average of the subsections is computed. It is computationally expensive when processing large‐scale sequences. In this paper, a quantum algorithm for ADPAAD is proposed, which can divide the subsequence elements and compute the average in parallel. The quantum algorithm can achieve polynomial speedups on the number of subsequences and the length of subsequences over its classical counterpart. [ABSTRACT FROM AUTHOR]

The key to generating tailored suggestions in the scenic location recommendation scene is how to model the diverse tourism environments in order to correctly acquire visitor preferences and scenic spot tourism features. However, most existing recommendation algorithms focus on the spatiotemporal background modeling of historical tourism trajectories. Only tourists' preferences are understood, and the rich heterogeneous tourism information such as tourists' personal tourism constraints and scenic spots' tourism attributes are ignored. In this paper, we proposed a multiple neural collaborative filtering attraction recommendation architecture (MNCF‐AR). To begin, we learn the tourism feature representation of tourists by modeling diverse tourism contexts, and then we create the tourism trajectory background of tourists using a large number of actual tourism logs to achieve the entire feature representation of tourists. Second, to learn the feature vector of scenic spots in the context, the tourism heterogeneous network map is used to build the scenic spot attribute background, the self‐attention network to learn the scenic spot sequence learning, and a neural network to project each scenic spot into a unified potential feature space. Finally, the multi‐neural collaborative filtering method is utilized to forecast the difference in scores between visitors and scenic sites so that tailored scenic spots may be recommended. Extensive experiments on mainstream datasets, such as MaFengwo, New York, Tokyo and Xi'an, show that the proposed method can effectively and accurately recommend attractions for users. © 2023 Institute of Electrical Engineer of Japan and Wiley Periodicals LLC. [ABSTRACT FROM AUTHOR]

Summary: In recent years, neighbor discovery techniques using directional antennas have attracted widespread attention. Most currently available directional neighbor discovery techniques are designed based on two‐dimensional (2D) space. Although these algorithms can accomplish the discovery between nodes, the algorithm portability is poor for three‐dimensional (3D) platforms, and the application scenarios are limited since new communication scenarios such as unmanned aerial vehicle (UAV) groups and maritime fleets emerge where information needs to be delivered in real time and nodes are located in 3D space. This paper proposes a new deterministic directional neighbor discovery algorithm in 3D space named 3D scan‐based algorithm (3D‐SBA) to meet the needs of the line‐of‐sight (LOS) scenes. Four existing neighbor discovery algorithms, namely, SBA‐based random mode selection (SBA‐R), quorum, complete random algorithm (CRA), and SBA‐based leader election algorithm (LE), have been extended to our proposed 3D algorithm model for simulation and comparative analysis with 3D‐SBA. The simulation results show that the 3D‐SBA algorithm consumes 51.15%, 180.20%, 9.48%, and 17.49% of the time slots compared with the four existing algorithms mentioned above. However, the quorum algorithm has a very high node collision rate, up to 92.11%. Ultimately, the 3D‐SBA algorithm has the best performance considering the conflicts and the density of network nodes. [ABSTRACT FROM AUTHOR]

In this paper, we focus on solving a distributed convex aggregative optimization problem in a network, where each agent has its own cost function which depends not only on its own decision variables but also on the aggregated function of all agents' decision variables. The decision variable is constrained within a feasible set. In order to minimize the sum of the cost functions when each agent only knows its local cost function, we propose a distributed Frank–Wolfe algorithm based on gradient tracking for the aggregative optimization problem where each node maintains two estimates, namely an estimate of the sum of agents' decision variable and an estimate of the gradient of global function. The algorithm is projection‐free, but only involves solving a linear optimization to get a search direction at each step. We show the convergence of the proposed algorithm for convex and smooth objective functions over a time‐varying network. Finally, we demonstrate the convergence and computational efficiency of the proposed algorithm via numerical simulations. [ABSTRACT FROM AUTHOR]

Summary: In this paper, we introduce a method for reasoning with words based on hedge algebra using linguistic cognitive map (핃ℂ필). Our model consists of a set of vertices and edges whose values are linguistic variables that are constrained by a linguistic lattice. The algorithm for the system studied consists of fuzzification, reasoning, and defuzzification. Further, the total effect between any two vertices in the 핃ℂ필 is computed. [ABSTRACT FROM AUTHOR]

Summary: This paper investigates the identification problem of an output‐error nonlinear system with saturation and dead‐zone nonlinearity. Introducing a switching function and by means of the auxiliary model identification idea, an auxiliary model hierarchical least squares‐based iterative algorithm is proposed for estimating the parameters of the nonlinear system. Based on the hierarchical identification model, an auxiliary model hierarchical gradient‐based iterative algorithm is presented for the nonlinear system by utilizing the gradient search. In order to take full advantage of the system data, an auxiliary model hierarchical multi‐innovation gradient‐based iterative algorithm is derived for the nonlinear system according to the multi‐innovation identification theory. Finally, the numerical simulation results illustrate the effectiveness of the proposed algorithms. [ABSTRACT FROM AUTHOR]

Summary: This paper addresses the combined estimation issues of the parameters and states for fractional‐order Hammerstein state space systems with colored noises. An extended state estimator is derived by using the parameter estimates to replace the unknown system parameters in Kalman filter. The hierarchical identification principle is introduced to solve the unknown parameters of measurement noises. By introducing the forgetting factor, an extended Kalman filtering‐based hierarchical forgetting factor stochastic gradient algorithm is presented to estimate the unknown states, parameters and fractional‐order. A numerical example is respectively presented to demonstrate the feasibility of the proposed identification algorithm. It can be seen that the estimation errors are relatively small, which reflects the proposed algorithms have good identification effect. [ABSTRACT FROM AUTHOR]

Summary: This paper mainly investigates the issue of parameter identification for the fractional‐order input nonlinear output error autoregressive (IN‐OEAR) model. In order to avoid the problem of large computation of redundant parameter estimation, the output form of the system can be expressed by a linear combination of unknown parameters through the key term separation. Through employing the hierarchial identification principle, the fractional‐order IN‐OEAR model is decomposed into two sub‐models with a smaller number of parameters. On the basis of the recursive identification methods, a recursive least squares sub‐algorithm and a gradient stochastic sub‐algorithm are proposed to estimate the parameters and the fractional‐order, respectively. With the aim of achieving more accurate parameter estimates, a two‐stage multi‐innovation least recursive algorithm is proposed by means of the multi‐innovation identification theory. The numerical simulation results test the effectiveness of the proposed methods. [ABSTRACT FROM AUTHOR]

This paper studies distributed convex optimization problems over an undirected network where all nodes cooperate to minimize a sum of local objective functions. Each local objective function is further assumed to be an average of several convex instantaneous functions. By incorporating the stochastic averaging gradient into the distributed first‐order primal‐dual method, a stochastic averaging gradient algorithm with multi‐step communication is proposed to solve the optimization problem. For each node, one randomly selected gradient of an instantaneous function is evaluated per iteration, which effectively reduces the computation cost of the algorithm. Based on conditions of strong convexity and Lipschitz continuity of the local instantaneous functions, a linear convergence rate of the proposed algorithm is guaranteed. Numerical simulations on the logistic regression problem demonstrate the performance of the algorithm and correctness of the theoretical results. [ABSTRACT FROM AUTHOR]

In this paper, we propose a fast Alikhanov algorithm with nonuniform time steps for a two dimensional distributed‐order time–space fractional advection–dispersion equation. First, an efficient fast Alikhanov algorithm on the general nonuniform time steps for the evaluation of Caputo fractional derivative is presented to sharply reduce the computational work and storage, and are applied to the distributed‐order time fractional derivative or multi‐term time fractional derivative under the nonsmooth regularity assumptions. And a generalized discrete fractional Grönwall inequality is extended to multi‐term fractional derivative or distributed‐order fractional derivative for analyzing theoretically our algorithm. Then the stability and convergence of time semi‐discrete scheme are investigated. Furthermore, we derive the corresponding fully discrete scheme by finite element method and discuss its convergence. At last, the given numerical examples adequately confirm the correctness of theoretical analysis and compare the computing effectiveness between the fast algorithm and the direct method. [ABSTRACT FROM AUTHOR]

Antenna array synthesis is quite a popular topic in electromagnetics and finding suitable array parameter values is a challenging nonlinear engineering problem in this field. In recent years, it has been realized that optimization algorithms can be used to achieve desired solutions in this area. Besides, improvements in the optimization algorithms make it possible to perform synthesis processes on different array structures and to obtain better results. In this paper, a method based on a combination of ant lion optimizer (ALO) and sequential quadratic programming (SQP) is proposed for the concentric circular antenna array (CCAA) synthesis. Excitation amplitudes of array elements are optimized for CCAAs with low maximum sidelobe level (MSL), narrow first null beamwidth (FNBW), and low dynamic range ratio (DRR). The results of proposed ALO‐SQP method are compared with those of 11 different algorithms: ALO, moth flame optimizer (MFO), SQP, symbiotic organisms search (SOS), biogeography based optimization (BBO), opposition‐based gravitational search algorithm (OGSA), cat swarm optimization (CSO), firefly algorithm (FA), evolutionary programming (EP), backtracking search optimization algorithm (BSA), and seeker optimization algorithm (SOA). The comparisons indicate that the CCAAs synthesis using the proposed method presents good MSLs, FNBWs, and DRRs. [ABSTRACT FROM AUTHOR]

This paper aims to present an overview of Semiparametric additive models. An estimation of the finite‐parameters of semiparametric regression models that involve additive nonparametric components is explained, including their historical background. In addition, three different smoothing techniques are considered in order to show the working procedures of the estimators and to explore their statistical properties: smoothing splines, kernel smoothing and local linear regression. These methods are compared with respect to both their theoretical and practical behaviors. A simulation study and a real data example are carried out to reveal the performances of the three methods. Accordingly, the advantages and disadvantages of each method regarding semiparametric additive models are presented based on their comparative scores using determined evaluation metrics for loss of information. This article is categorized under:Statistical Learning and Exploratory Methods of the Data Sciences > Modeling MethodsStatistical and Graphical Methods of Data Analysis > Multivariate AnalysisStatistical Models > Semiparametric Models [ABSTRACT FROM AUTHOR]

This paper mainly studies mixed integer linear programming (MILP)‐based cryptanalysis on round‐reduced NBC algorithm with generalized Feistel structure. First, each component of the algorithm is equivalently described by linear inequality equations, and the propagation rules of differential characteristics and linear approximation are described, and an automatic search algorithm model of differential mode and linear mask mode based on MILP is established, and the minimum number of active S‐boxes and the corresponding differential mode and linear mask mode paths are obtained. Second, according to the NBC algorithm's 16‐bit block pull‐wire position permutation characteristics, the optimal full diffusion rounds of NBC‐128 algorithm and NBC‐256 algorithm are obtained by using approximate matrix multiplication theory to be six and eight respectively. Finally, based on the optimal number of full diffusion rounds of the algorithm, an automatic search algorithm model of impossible differential cryptanalysis is established, and the set of input differential patterns is traversed to obtain 11‐round impossible differential distinguishers of NBC‐128 algorithm and 14‐round impossible differential distinguishers of NBC‐256 algorithm respectively. [ABSTRACT FROM AUTHOR]

The airborne transient electromagnetics method has been widely used in geophysical exploration in recent years, but it still faces challenges in balancing the accuracy and efficiency of electromagnetic data interpretation. As far as forward modelling is concerned, the higher the dimension of the geophysical model, the higher the accuracy of data interpretation, but, correspondingly, the more computing resources need to be consumed, which will greatly reduce investigation efficiency and practicability. In this paper, the spectral element method is first introduced for solving the 2.5‐dimensional forward modelling of the airborne transient electromagnetic system, which has a smaller computing scale than three‐dimensional modelling and is closer to the actual geological structure than either one‐ or two‐dimensional modelling. In the forward algorithm, a non‐uniform quadrilateral structured mesh is adopted to simplify the computing scale, and the Talbot algorithm rather than Gaver–Stefest algorithm is applied to the inverse Laplace transform to improve the numerical precision of this conversion. Moreover, we use parallel computing technology to improve the algorithm efficiency while keeping satisfactory accuracy. The study shows that, whether a low‐resistivity or high‐resistivity layered geophysical model, the numerical solutions of the proposed spectral element method forward algorithm agree well with the analytical solutions of the corresponding models; furthermore, the key factors affecting the accuracy of the numerical solution are analysed by experiments. Finally, we successfully applied it to the 2.5‐dimensional geoelectric model simulation. [ABSTRACT FROM AUTHOR]

In this paper, we consider the distributed bandit convex optimization of time‐varying objective functions over a network. By introducing perturbations into the objective functions, we design a deterministic difference and a randomized difference to replace the gradient information of the objective functions and propose two classes of gradient‐free distributed algorithms. We prove that both the two classes of algorithms achieve regrets of O(T3/4)$$ O\left({T}^{3/4}\right) $$ for convex objective functions and O(T2/3)$$ O\left({T}^{2/3}\right) $$ for strongly convex objective functions, with respect to the time index T$$ T $$ and consensus of the estimates established as well. Simulation examples are given justifying the theoretical results. [ABSTRACT FROM AUTHOR]

Research on global harmonic mitigation against distributed and high‐proportioned nonlinear loads in modern distribution networks has received extensive attention. In this paper, a distributed compensation method for active power filters (APFs) is proposed, which utilizes a small number of APFs with adjustable reference to alleviate the global voltage distortion caused by a large number of distributed nonlinear loads. The model predictive control (MPC) is employed to calculate the optimal current reference for compensators at each optimization moment by predicting the system's performance in a certain future time period. Furthermore, the Kalman filter (KF) algorithm is used to estimate the initial harmonic voltage for the MPC, reducing the unfavorable effects of the model uncertainty and measurement noise. The test results based on a seven‐bus distribution network in MATLAB are provided to verify the effectiveness of the proposed method. © 2023 Institute of Electrical Engineer of Japan and Wiley Periodicals LLC. [ABSTRACT FROM AUTHOR]

Geo‐materials are generally regarded as multi‐phase structural systems, which are composed of particles, pores, and fissures. Generally, the shape and size of particles have considerable influence on the physical and mechanical properties of geo‐materials. Based on the theory of random angular bend (RAB) algorithm, this paper presented a method to finely generate the three‐dimensional (3D) random particle model via the superposition of two‐dimensional (2D) particle profiles, and this proposed method was coded in Python. According to the generation procedure, the relevant point cloud data should be generated, and with the aid of the point cloud normal vector calculation and Poisson reconstruction technique, the required 3D particle profiles can be obtained. Subsequently, three shape descriptors are selected to describe the shape characteristics of generated particles, and accordingly, the quantitative relationships between the shape descriptors and the input controlling parameters are established to accurately control the shape of generated particles. Finally, the generated geo‐material particles are implemented into the particle flow code (PFC3D) to construct the clump library, and an example about a 3D soil–rock mixture model was taken to validate the performance of the proposed method for numerical simulation. The results show that this study provides a useful strategy for the simulation of the geo‐materials based on the RAB theory. [ABSTRACT FROM AUTHOR]

Summary: Designing an energy efficient and durable wireless sensor networks (WSNs) is a key challenge as it personifies potential and reactive functionalities in harsh antagonistic environment at which wired system deployment is completely infeasible. Majority of the clustering mechanisms contributed to the literature concentrated on augmenting network lifetime and energy stability. However, energy consumption incurred by cluster heads (CHs) are high and thereby results in minimized network lifetime and frequent CHs selection. In this paper, a modified whale‐dragonfly optimization algorithm and self‐adaptive cuckoo search‐based clustering strategy (MWIDOA‐SACS) is proposed for sustaining energy stability and augment network lifetime. In specific, MWIDOA‐SACS is included for exploiting the fitness values that aids in determining two optimal nodes that are selected as optimal CH and cluster router (CR) nodes in the network. In MWIDOA, the search conduct of dragon flies is completely updated through whale optimization algorithm (WOA) for preventing load balancing at CHs. It minimized the overhead of CH by adopting CHs and CR for collecting information from cluster members and transmitting the aggregated data from CHs to the base station (BS). It included self‐adaptive cuckoo search (SACS) for achieving sink mobility using radius, energy stability, received signal strength, and throughput for achieving optimal data transmission process after partitioning the network into unequal clusters. Simulation experiments of the proposed MWIDOA‐SACS confirmed better performance in terms of total residual energy by 21.28% and network lifetime by 26.32%, compared to the competitive CH selection strategies. [ABSTRACT FROM AUTHOR]

This paper proposes a multitasking Demura algorithm based on backlight modulation and liquid crystal voltage adjustment that significantly increase the luminance uniformity and improves the details of high gray image without saturation issues. The multitasking Demura benefit was experimentally validated in a 55‐inch splicing module display, and the experimental results show that the multitasking Demura can eliminate severe mura, increasing the module's luminance uniformity from 34%, 60% and 88% to 83%, 95% and 98% at L25, L128 and L240 gray levels. [ABSTRACT FROM AUTHOR]

To ensure the uniformity of panel image quality, it is necessary to gamma correct the normal and FDC（full display camera） regions of the panel, but the gamma TT（tack time） is particularly long, especially the FDC takes about 110 seconds, resulting in lower production efficiency. Currently, the FDC correction algorithm uses the gamma value of the previous panel as the initial value, and its average error is about 60, and the error is large. To reduce the FDC gamma TT, this paper proposes a new algorithm based on CNN, which inputs normal gamma and predicts FDC gamma. The predicted results are taken as the starting value of the gamma in the FDC region, the starting value error is small and the FDC gamma TT is greatly shortened. Experimental results show that compared with the existing algorithm, the accuracy of the initial value of the FDC region is increased by 10 times. FDC gamma TT was reduced by about 3.5 times. [ABSTRACT FROM AUTHOR]

Boosting has proven its superiority by increasing the diversity of base classifiers, mainly in various classification problems. In reality, target variables in classification often are formed by numerical variables, in possession of ordinal information. However, existing boosting algorithms for classification are unable to reflect such ordinal target variables, resulting in non‐optimal solutions. In this paper, we propose a novel algorithm of ordinal encoding adaptive boosting (AdaBoost) using a multi‐dimensional encoding scheme for ordinal target variables. Extending an original binary‐class AdaBoost, the proposed algorithm is equipped with a multi‐class exponential loss function. We show that it achieves the Bayes classifier and establishes forward stagewise additive modeling. We demonstrate the performance of the proposed algorithm with a base learner as a neural network. Our experiments show that it outperforms existing boosting algorithms in various ordinal datasets. [ABSTRACT FROM AUTHOR]